使用 PyTorch 進行影像深度學習
Michal Oleszak
Machine Learning Engineer



bbox1 = [50, 50, 150, 150] bbox2 = [100, 100, 200, 200]bbox1 = torch.tensor(bbox1).unsqueeze(0) bbox2 = torch.tensor(bbox2).unsqueeze(0)
from torchvision.ops import box_iou
iou = box_iou(bbox1, bbox2)
print(iou)
tensor([[0.1429]])

model.eval() with torch.no_grad():output = model(input_image)print(output)
[{'boxes': tensor([[ 42.8553, 271.9481, 180.6003, 346.7082],
[191.6016, 80.4759, 247.8009, 387.5475], ....),
'scores': tensor([1.0000, 1.0000, 0.9998, ... ]),
'labels': tensor([18, 1, 20, 18, 18, 18 ...])
}]
boxes = output[0]["boxes"]scores = output[0]["scores"]


非極大值抑制:選出最相關邊界框的常用技巧
Non-max:丟棄對含有物件之信心分數較低的框
Suppression:丟棄 IoU 較低的框
from torchvision.ops import nmsbox_indices = nms( boxes=boxes, scores=scores, iou_threshold=0.5, ) print(box_indices)
tensor([ 0, 1, 2, 8])
filtered_boxes = boxes[box_indices]
Boxes:形狀為 [N, 4] 的邊界框座標張量
Scores:形狀為 [N]、各框的信心分數張量
iou_threshold:介於 0.0 到 1.0 的門檻
輸出:篩選後邊界框的索引
使用 PyTorch 進行影像深度學習